aboutsummaryrefslogtreecommitdiff
path: root/kernel/sched_clock.c
blob: 42b81fa38cbd254987dbedef0f0bd047766d36e3 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
/*
 * sched_clock for unstable cpu clocks
 *
 *  Copyright (C) 2008 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
 *
 * Based on code by:
 *   Ingo Molnar <mingo@redhat.com>
 *   Guillaume Chazarain <guichaz@gmail.com>
 *
 * Create a semi stable clock from a mixture of other events, including:
 *  - gtod
 *  - jiffies
 *  - sched_clock()
 *  - explicit idle events
 *
 * We use gtod as base and the unstable clock deltas. The deltas are filtered,
 * making it monotonic and keeping it within an expected window.  This window
 * is set up using jiffies.
 *
 * Furthermore, explicit sleep and wakeup hooks allow us to account for time
 * that is otherwise invisible (TSC gets stopped).
 *
 * The clock: sched_clock_cpu() is monotonic per cpu, and should be somewhat
 * consistent between cpus (never more than 1 jiffies difference).
 */
#include <linux/sched.h>
#include <linux/percpu.h>
#include <linux/spinlock.h>
#include <linux/ktime.h>
#include <linux/module.h>


#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK

struct sched_clock_data {
	/*
	 * Raw spinlock - this is a special case: this might be called
	 * from within instrumentation code so we dont want to do any
	 * instrumentation ourselves.
	 */
	raw_spinlock_t		lock;

	unsigned long		tick_jiffies;
	u64			prev_raw;
	u64			tick_raw;
	u64			tick_gtod;
	u64			clock;
};

static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);

static inline struct sched_clock_data *this_scd(void)
{
	return &__get_cpu_var(sched_clock_data);
}

static inline struct sched_clock_data *cpu_sdc(int cpu)
{
	return &per_cpu(sched_clock_data, cpu);
}

static __read_mostly int sched_clock_running;

void sched_clock_init(void)
{
	u64 ktime_now = ktime_to_ns(ktime_get());
	unsigned long now_jiffies = jiffies;
	int cpu;

	for_each_possible_cpu(cpu) {
		struct sched_clock_data *scd = cpu_sdc(cpu);

		scd->lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
		scd->tick_jiffies = now_jiffies;
		scd->prev_raw = 0;
		scd->tick_raw = 0;
		scd->tick_gtod = ktime_now;
		scd->clock = ktime_now;
	}

	sched_clock_running = 1;
}

/*
 * update the percpu scd from the raw @now value
 *
 *  - filter out backward motion
 *  - use jiffies to generate a min,max window to clip the raw values
 */
static void __update_sched_clock(struct sched_clock_data *scd, u64 now)
{
	unsigned long now_jiffies = jiffies;
	long delta_jiffies = now_jiffies - scd->tick_jiffies;
	u64 clock = scd->clock;
	u64 min_clock, max_clock;
	s64 delta = now - scd->prev_raw;

	WARN_ON_ONCE(!irqs_disabled());

	min_clock = scd->tick_gtod +
		(delta_jiffies ? delta_jiffies - 1 : 0) * TICK_NSEC;

	if (unlikely(delta < 0)) {
		clock++;
		goto out;
	}

	/*
	 * The clock must stay within a jiffie of the gtod.
	 * But since we may be at the start of a jiffy or the end of one
	 * we add another jiffy buffer.
	 */
	max_clock = scd->tick_gtod + (2 + delta_jiffies) * TICK_NSEC;

	if (unlikely(clock + delta > max_clock)) {
		if (clock < max_clock)
			clock = max_clock;
		else
			clock++;
	} else {
		clock += delta;
	}

 out:
	if (unlikely(clock < min_clock))
		clock = min_clock;

	scd->prev_raw = now;
	scd->clock = clock;
}

static void lock_double_clock(struct sched_clock_data *data1,
				struct sched_clock_data *data2)
{
	if (data1 < data2) {
		__raw_spin_lock(&data1->lock);
		__raw_spin_lock(&data2->lock);
	} else {
		__raw_spin_lock(&data2->lock);
		__raw_spin_lock(&data1->lock);
	}
}

u64 sched_clock_cpu(int cpu)
{
	struct sched_clock_data *scd = cpu_sdc(cpu);
	u64 now, clock;

	if (unlikely(!sched_clock_running))
		return 0ull;

	WARN_ON_ONCE(!irqs_disabled());
	now = sched_clock();

	if (cpu != raw_smp_processor_id()) {
		/*
		 * in order to update a remote cpu's clock based on our
		 * unstable raw time rebase it against:
		 *   tick_raw		(offset between raw counters)
		 *   tick_gotd          (tick offset between cpus)
		 */
		struct sched_clock_data *my_scd = this_scd();

		lock_double_clock(scd, my_scd);

		now -= my_scd->tick_raw;
		now += scd->tick_raw;

		now -= my_scd->tick_gtod;
		now += scd->tick_gtod;

		__raw_spin_unlock(&my_scd->lock);
	} else {
		__raw_spin_lock(&scd->lock);
	}

	__update_sched_clock(scd, now);
	clock = scd->clock;

	__raw_spin_unlock(&scd->lock);

	return clock;
}

void sched_clock_tick(void)
{
	struct sched_clock_data *scd = this_scd();
	unsigned long now_jiffies = jiffies;
	u64 now, now_gtod;

	if (unlikely(!sched_clock_running))
		return;

	WARN_ON_ONCE(!irqs_disabled());

	now = sched_clock();
	now_gtod = ktime_to_ns(ktime_get());

	__raw_spin_lock(&scd->lock);
	__update_sched_clock(scd, now);
	/*
	 * update tick_gtod after __update_sched_clock() because that will
	 * already observe 1 new jiffy; adding a new tick_gtod to that would
	 * increase the clock 2 jiffies.
	 */
	scd->tick_jiffies = now_jiffies;
	scd->tick_raw = now;
	scd->tick_gtod = now_gtod;
	__raw_spin_unlock(&scd->lock);
}

/*
 * We are going deep-idle (irqs are disabled):
 */
void sched_clock_idle_sleep_event(void)
{
	sched_clock_cpu(smp_processor_id());
}
EXPORT_SYMBOL_GPL(sched_clock_idle_sleep_event);

/*
 * We just idled delta nanoseconds (called with irqs disabled):
 */
void sched_clock_idle_wakeup_event(u64 delta_ns)
{
	struct sched_clock_data *scd = this_scd();
	u64 now = sched_clock();

	/*
	 * Override the previous timestamp and ignore all
	 * sched_clock() deltas that occured while we idled,
	 * and use the PM-provided delta_ns to advance the
	 * rq clock:
	 */
	__raw_spin_lock(&scd->lock);
	scd->prev_raw = now;
	scd->clock += delta_ns;
	__raw_spin_unlock(&scd->lock);

	touch_softlockup_watchdog();
}
EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);

#endif

/*
 * Scheduler clock - returns current time in nanosec units.
 * This is default implementation.
 * Architectures and sub-architectures can override this.
 */
unsigned long long __attribute__((weak)) sched_clock(void)
{
	return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ);
}